Шум меток

Ensemble techniques are powerful ap- proaches that combine several weak learn- ers to build a stronger one. As a meta learning framework, ensemble techniques can easily be applied to many …...

AbstractBecause large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models …...

AbstractDeep neural networks (DNNs) have a high capacity to completely memorize noisy labels given sufficient training time, and its memorization unfortunately leads to performance degradation. Recently, virtual adversarial training (VAT) …...

AbstractThe conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in …...

AbstractSelf-training emerges as an important research line on domain adaptation. By taking the model’s prediction as the pseudo labels of the unlabeled data, self-training bootstraps the model with pseudo instances …...

AbstractWeakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it allows training models with noisy annotations …...